pip install "transformers[torch]>=5.7.0" torchvision torchcodec

from transformers import AutoModelForImageTextToText, AutoProcessor

model_id = "openbmb/MiniCPM-V-4.6"

processor = AutoProcessor.from_pretrained(model_id)
model = AutoModelForImageTextToText.from_pretrained(
    model_id, torch_dtype="auto", device_map="auto"
)

# Flash Attention 2 is recommended for better acceleration and memory saving,
# especially in multi-image and video scenarios.
# model = AutoModelForImageTextToText.from_pretrained(
#     model_id,
#     torch_dtype=torch.bfloat16,
#     attn_implementation="flash_attention_2",
#     device_map="auto",
# )

messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/openbmb/DemoCase/resolve/main/refract.png"},
            {"type": "text", "text": "What causes this phenomenon?"},
        ],
    }
]

downsample_mode = "16x"  # Using `downsample_mode="4x"` for Finer Detail

inputs = processor.apply_chat_template(
    messages, tokenize=True, add_generation_prompt=True,
    return_dict=True, return_tensors="pt",
    downsample_mode=downsample_mode,
    max_slice_nums=36,
).to(model.device)

generated_ids = model.generate(**inputs, downsample_mode=downsample_mode, max_new_tokens=512)
generated_ids_trimmed = [
    out_ids[len(in_ids):] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
]
output_text = processor.batch_decode(
    generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
)
print(output_text[0])

messages = [
    {
        "role": "user",
        "content": [
            {"type": "video", "url": "https://huggingface.co/datasets/openbmb/DemoCase/resolve/main/football.mp4"},
            {"type": "text", "text": "Describe this video in detail. Follow the timeline and focus on on-screen text, interface changes, main actions, and scene changes."},
        ],
    }
]

downsample_mode = "16x"  # Using `downsample_mode="4x"` for Finer Detail

inputs = processor.apply_chat_template(
    messages, tokenize=True, add_generation_prompt=True,
    return_dict=True, return_tensors="pt",
    downsample_mode=downsample_mode,
    max_num_frames=128,
    stack_frames=1,
    max_slice_nums=1,
    use_image_id=False,
).to(model.device)

generated_ids = model.generate(**inputs, downsample_mode=downsample_mode, max_new_tokens=2048)
generated_ids_trimmed = [
    out_ids[len(in_ids):] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
]
output_text = processor.batch_decode(
    generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
)
print(output_text[0])

pip install "transformers[serving]>=5.7.0"

transformers serve openbmb/MiniCPM-V-4.6 --port 8000 --host 0.0.0.0 --continuous-batching

curl -s http://localhost:8000/v1/chat/completions \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "openbmb/MiniCPM-V-4.6",
    "messages": [{
      "role": "user",
      "content": [
        {"type": "image_url", "image_url": {"url": "https://huggingface.co/datasets/openbmb/DemoCase/resolve/main/refract.png"}},
        {"type": "text", "text": "What causes this phenomenon?"}
      ]
    }]
  }'

curl -s http://localhost:8000/v1/chat/completions -H 'Content-Type: application/json' -d '{
  "model": "openbmb/MiniCPM-V-4.6",
  "messages": [{"role": "user", "content": [
    {"type": "text", "text": "the weather of Beijing"}
  ]}],
  "tools": [{
    "type": "function",
    "function": {
      "name": "get_weather",
      "description": "Get the current weather for a given location",
      "parameters": {
        "type": "object",
        "properties": {
          "location": {"type": "string", "description": "City name"}
        },
        "required": ["location"]
      }
    }
  }]
}'

{
    "id": "f4f09c7d-8045-4cb1-ade9-07aa5dee637d",
    "choices": [
        {
            "finish_reason": "stop",
            "index": 0,
            "message": {
                "content": "I need to check the current weather for Beijing, so I will call the get_weather function.\n\n<tool_call>\n<function=get_weather>\n<parameter=location>\nBeijing\n</parameter>\n</function>\n</tool_call>",
                "role": "assistant"
            }
        }
    ],
    "created": 1778748859,
    "model": "openbmb/MiniCPM-V-4.6@main",
    "object": "chat.completion",
    "usage": {
        "completion_tokens": 47,
        "prompt_tokens": 283,
        "total_tokens": 330
    }
}

import re

_PATTERN = re.compile(
    r'(```[\s\S]*?```'       # fenced code blocks
    r'|`[^`]+`'              # inline code
    r'|\$\$[\s\S]*?\$\$'     # display math
    r'|\$[^$]+\$'            # inline math
    r'|\\$[\s\S]*?\\$'     # $...$
    r'|\\

$$[\s\S]*?\\$$

'     # 

$$...$$


    r')'
    r'|(?<!\\)(?:\\r\\n|\\[nr])'
)

def normalize_response_text(text: str) -> str:
    """
    Lightweight post-processing: Converts literal '\\n' to actual newlines, 
    while protecting code blocks, inline code, and LaTeX commands.
    """
    if not isinstance(text, str) or "\\" not in text:
        return text
    return _PATTERN.sub(lambda m: m.group(1) or '\n', text)

@proceedings{yu2025minicpmv45cookingefficient,
      title={MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe}, 
      author={Tianyu Yu and Zefan Wang and Chongyi Wang and Fuwei Huang and Wenshuo Ma and Zhihui He and Tianchi Cai and Weize Chen and Yuxiang Huang and Yuanqian Zhao and others},
      year={2025},
      url={https://arxiv.org/abs/2509.18154}, 
}

@article{yao2024minicpm,
  title={MiniCPM-V: A GPT-4V Level MLLM on Your Phone},
  author={Yao, Yuan and Yu, Tianyu and Zhang, Ao and Wang, Chongyi and Cui, Junbo and Zhu, Hongji and Cai, Tianchi and Li, Haoyu and Zhao, Weilin and He, Zhihui and others},
  journal={arXiv preprint arXiv:2408.01800},
  year={2024}
}